© 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. 15-GEMMASCOPE-2-RES-16K
    7. 6120
    Prev
    Next
    INDEX
    Explanations

    starts of names

    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_15_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
    ---------
    0.85
    -----------
    0.82
    ---------------
    0.76
    GEM
    0.75
    -------------
    0.74
    ----------
    0.71
    --------------
    0.71
    ------
    0.67
    Hr
    0.67
    -----
    0.67
    POSITIVE LOGITS
    heem
    2.74
    踹
    2.67
    andae
    2.67
    issippi
    2.65
    مني
    2.64
    탄소년
    2.58
    óstico
    2.57
    ayv
    2.53
     linebacker
    2.52
    ynit
    2.51
    Activations Density 0.151%

    No Known Activations