© 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. 158652
    Prev
    Next
    INDEX
    Explanations

    technology that

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

    beginnings (mouth, entrance, first)

    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
    CDCl
    0.51
    Primer
    0.43
    ौरी
    0.43
    lika
    0.42
     οποίο
    0.42
    εται
    0.41
    inairement
    0.41
     }}"
    0.41
    ől
    0.40
     iii
    0.40
    POSITIVE LOGITS
     wielding
    0.48
     イメージ
    0.47
     Scandal
    0.46
     Findings
    0.45
     スク
    0.45
     avocado
    0.45
    bies
    0.44
     Laurence
    0.44
     Esch
    0.44
     Schmidt
    0.44
    Activations Density 0.000%

    No Known Activations