© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 61496
    Prev
    Next
    INDEX
    Explanations

    hanging gift, work access

    np_acts-logits-general · gemini-2.5-flash-lite

    |Ancestries| inside | currency | can negatively | Consider cultural | just about | if the | both our | Weekday( |

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Maintain
    0.50
     программ
    0.50
    єї
    0.48
     EMAIL
    0.48
    @
    0.47
     肌
    0.46
     MAC
    0.46
    ר
    0.46
     OBJECTTYPE
    0.45
    ரா
    0.44
    POSITIVE LOGITS
    اور
    0.50
    andolo
    0.47
     palav
    0.45
     Volumen
    0.43
     cityscape
    0.43
    adan
    0.42
     Prav
    0.41
     entend
    0.41
    .$-
    0.41
    स्तक
    0.41
    Activations Density 0.000%

    No Known Activations