© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77089
    Prev
    Next
    INDEX
    Explanations

    claims and liability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    予想
    -0.84
    !("{
    -0.79
     "¿
    -0.78
    的名字
    -0.75
    consent
    -0.72
    接種
    -0.71
    Cactus
    -0.68
    襷
    -0.68
     grooves
    -0.68
    っこ
    -0.68
    POSITIVE LOGITS
     claims
    5.44
     claim
    5.34
     Claims
    4.06
    claim
    4.06
    claims
    4.03
     Claim
    3.97
    Claims
    3.97
    Claim
    3.91
     claimed
    3.45
     claiming
    3.44
    Activations Density 0.073%

    No Known Activations