© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 113382
    Prev
    Next
    INDEX
    Explanations

    establish gut

    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
     ballpark
    0.48
     McC
    0.46
     Roundtable
    0.45
     Cooling
    0.44
     Pledge
    0.43
     的
    0.43
     Measure
    0.43
     Textbook
    0.43
    麴
    0.43
     Calculus
    0.43
    POSITIVE LOGITS
     overcome
    0.46
    emiz
    0.44
    amil
    0.42
     incompet
    0.42
     incompat
    0.42
     pernicious
    0.40
    getpath
    0.39
    paar
    0.39
    avourite
    0.39
    ambre
    0.39
    Activations Density 0.007%

    No Known Activations