© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 13783
    Prev
    Next
    INDEX
    Explanations

    purpose is

    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_22_width_262k_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
    =((
    0.89
    ム
    0.87
    ョ
    0.85
     sikap
    0.84
    અમ
    0.83
    лор
    0.82
    opathic
    0.82
    ards
    0.82
    UpDown
    0.81
    ڑ
    0.81
    POSITIVE LOGITS
    প্রণ
    1.13
    চার
    1.00
    FUL
    0.97
    ktionen
    0.96
    क्रिप्शन
    0.93
    чения
    0.90
     isto
    0.86
    altro
    0.85
     সার্ভ
    0.81
    ineuse
    0.81
    Activations Density 0.046%

    No Known Activations