© 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-16K
    7. 12718
    Prev
    Next
    INDEX
    Explanations

    evaluative statements followed by clauses

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

    crucial, important, vital, unusual

    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_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
     فهي
    0.41
    مره
    0.37
    ()?;
    0.37
    ....
    0.37
     preval
    0.36
    abr
    0.36
     dificuldade
    0.36
    其
    0.36
    राव
    0.36
    \%$
    0.35
    POSITIVE LOGITS
    こういう
    0.58
     να
    0.56
     having
    0.56
     داشتن
    0.54
     imati
    0.53
    avoir
    0.52
     faptul
    0.52
     enviar
    0.51
     знать
    0.50
    having
    0.49
    Activations Density 0.347%

    No Known Activations