© 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. 179382
    Prev
    Next
    INDEX
    Explanations

    gift ideas

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

    son/daughter

    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
    -
    0.59
    are
    0.55
    is
    0.51
    z
    0.50
    met
    0.50
    ck
    0.49
    con
    0.48
    can
    0.47
    door
    0.47
    ''
    0.47
    POSITIVE LOGITS
     enviar
    0.53
    GONDOR
    0.53
     erleben
    0.49
     дзяржа
    0.48
    )^{[\
    0.48
     NYPD
    0.47
     wechseln
    0.47
     LETTERS
    0.46
    setAdapter
    0.46
     själ
    0.45
    Activations Density 0.001%

    No Known Activations