© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 136934
    Prev
    Next
    INDEX
    Explanations

    technical discussions and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    엽
    0.51
    ност
    0.46
     이것
    0.45
    писи
    0.44
     sequencer
    0.43
     सर
    0.43
     হস্তে
    0.43
    жет
    0.42
     갖
    0.42
    齎
    0.42
    POSITIVE LOGITS
    et
    0.48
    i
    0.48
    جين
    0.47
    স্ব
    0.46
     النوم
    0.45
    mfenced
    0.45
    people
    0.44
     ausgew
    0.42
    iques
    0.42
    كم
    0.41
    Activations Density 0.002%

    No Known Activations