© 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. 96178
    Prev
    Next
    INDEX
    Explanations

    collocations with conditional words

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

    Crash Bandicoot, cloning, Linux, inspections

    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
    
    0.49
     denture
    0.45
    ガス
    0.44
    ल्ली
    0.44
     get
    0.43
    क्योंकि
    0.43
     excav
    0.43
     gas
    0.42
     depuis
    0.42
     diagonal
    0.42
    POSITIVE LOGITS
    ?'
    0.52
    ?’
    0.52
    ()?
    0.52
     Verständ
    0.48
    ?\
    0.47
    ?:
    0.47
    celona
    0.47
    爱你
    0.47
    ؟!
    0.46
    Za
    0.46
    Activations Density 0.000%

    No Known Activations