© 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. 28862
    Prev
    Next
    INDEX
    Explanations

    earth dried and

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

    famine, Holodomor, genocide

    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
     farlo
    0.47
    ίναι
    0.43
    🟥
    0.43
    잦
    0.43
    ()];
    0.42
     oldValue
    0.42
    মোঃ
    0.42
    𝗄
    0.42
    offsetX
    0.42
    mixing
    0.41
    POSITIVE LOGITS
     અને
    0.55
     आणि
    0.53
    および
    0.53
     および
    0.47
     and
    0.47
     și
    0.46
     ਅਤੇ
    0.46
    嫻
    0.45
     و
    0.45
     మరియు
    0.44
    Activations Density 0.000%

    No Known Activations