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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 49223
    Prev
    Next
    INDEX
    Explanations

    invented things and markets

    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_65k_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
    =");
    0.49
    乨
    0.47
    Mode
    0.46
    Side
    0.46
    AddModel
    0.46
     కంటే
    0.46
    ';"+
    0.44
    Bounds
    0.44
    ımda
    0.44
     ascendent
    0.44
    POSITIVE LOGITS
    the
    0.46
     seves
    0.42
    જુ
    0.42
    ᒡ
    0.42
     ades
    0.41
    ten
    0.41
    tested
    0.41
    /*
    0.40
    need
    0.40
    ᆯ
    0.40
    Activations Density 0.001%

    No Known Activations