© 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. 40-GEMMASCOPE-2-RES-262K
    7. 14582
    Prev
    Next
    INDEX
    Explanations

    affords, accepts, supports

    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_40_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
    keep
    0.41
    eters
    0.40
    mover
    0.39
    ettle
    0.38
    Keep
    0.37
    sinh
    0.36
    Lub
    0.36
    담
    0.36
    чина
    0.36
    inear
    0.36
    POSITIVE LOGITS
     illusions
    0.45
     crooked
    0.44
     barcodes
    0.43
     infusions
    0.43
     bikes
    0.42
     immagine
    0.41
     delusions
    0.41
     ballots
    0.41
     hallucinations
    0.41
     dealings
    0.40
    Activations Density 0.000%

    No Known Activations