© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 3086
    Prev
    Next
    INDEX
    Explanations

    your personal information and credentials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     поме
    0.75
     Trusts
    0.75
    âmb
    0.73
    sekut
    0.73
    禄
    0.72
    acions
    0.71
     ngo
    0.71
     নো
    0.71
    igious
    0.70
    ฎ
    0.70
    POSITIVE LOGITS
     username
    1.75
     credentials
    1.70
    Username
    1.67
    username
    1.64
     Username
    1.58
     usernames
    1.51
     Credentials
    1.44
     login
    1.44
     passwords
    1.41
    用户名
    1.41
    Activations Density 0.478%

    No Known Activations