© 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. 6776
    Prev
    Next
    INDEX
    Explanations

    very + qualifier

    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
     from
    1.73
     for
    1.65
    ers
    1.61
     was
    1.58
    :
    1.58
     or
    1.56
     is
    1.56
    oped
    1.55
    <b>
    1.53
     the
    1.53
    POSITIVE LOGITS
    slightly
    2.03
    VERY
    1.84
    clearly
    1.82
     약간
    1.81
    simply
    1.80
     VERY
    1.80
    consciously
    1.79
     Possibly
    1.75
     조금
    1.75
    OWN
    1.74
    Activations Density 0.106%

    No Known Activations