© 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. 36020
    Prev
    Next
    INDEX
    Explanations

    absolute rights, majority shareholder, nice idea

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

    congratulations on achievements

    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
     Italian
    0.44
    description
    0.44
    علام
    0.44
    ”
    0.43
    qw
    0.41
    -
    0.40
    q
    0.40
    Description
    0.38
    0.38
     aria
    0.38
    POSITIVE LOGITS
     ፕሮ
    0.58
    णू
    0.52
     или
    0.52
     しっかり
    0.52
    ुरा
    0.51
     финанси
    0.51
     инженер
    0.51
     җиңү
    0.51
     דבר
    0.51
     financement
    0.50
    Activations Density 0.000%

    No Known Activations