© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4077
    Prev
    Next
    INDEX
    Explanations

    put followed by common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_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
    ublic
    1.77
    かもし
    1.52
     wiem
    1.47
    <sup>
    1.45
     dzien
    1.45
    <0xAE>
    1.43
    ppure
    1.42
    几何
    1.42
    トーク
    1.39
    <sub>
    1.38
    POSITIVE LOGITS
    یف
    2.29
    butyl
    1.92
    together
    1.87
    켓
    1.81
    sous
    1.81
    パクト
    1.80
    𝑔
    1.79
    话说
    1.79
    deviceName
    1.79
    terer
    1.79
    Activations Density 0.094%

    No Known Activations