© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 87836
    Prev
    Next
    INDEX
    Explanations

    terms and conditions, civil war, relationships, people

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

    issues of sex and exploitation

    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
    \...
    0.51
    ,\
    0.47
    …
    0.44
    acts
    0.43
    .\
    0.41
    ...\
    0.41
    Ens
    0.41
    oth
    0.41
     servicemen
    0.41
    ^{\
    0.40
    POSITIVE LOGITS
     völl
    0.56
     Blut
    0.53
     blau
    0.52
    و
    0.50
     cáps
    0.49
    یا
    0.49
    غراف
    0.49
     corte
    0.48
     recursos
    0.47
    olim
    0.47
    Activations Density 0.001%

    No Known Activations