© 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. 86873
    Prev
    Next
    INDEX
    Explanations

    email addresses and identifiers

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

    creating with @latest

    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
    owość
    0.44
     وسلم
    0.41
     supernatant
    0.41
    zeugt
    0.40
     وصحبه
    0.40
    )
    0.40
     renunci
    0.40
    ReaderWriter
    0.39
     inm
    0.39
     बंदी
    0.38
    POSITIVE LOGITS
     മതി
    0.53
    пу
    0.46
    intervals
    0.45
     ಅಪ
    0.43
     saturation
    0.43
     масштаб
    0.43
     максима
    0.42
    আবার
    0.42
    ⓐ
    0.42
     intervals
    0.42
    Activations Density 0.002%

    No Known Activations