© 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. 9-GEMMASCOPE-2-RES-262K
    7. 11374
    Prev
    Next
    INDEX
    Explanations

    crisis text line instruction

    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_9_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
    னர்
    2.39
    s
    2.22
    dı
    2.15
    ের
    2.13
    ς
    2.11
    ات
    2.10
     ramping
    2.06
    ″
    1.99
    াজ্ঞ
    1.98
    nya
    1.96
    POSITIVE LOGITS
    jší
    2.44
    ので
    2.34
    んじゃない
    1.79
     else
    1.78
    ुस्तान
    1.77
    zug
    1.77
    cek
    1.76
    ği
    1.75
    া
    1.73
     rechts
    1.69
    Activations Density 0.007%

    No Known Activations