© 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. 166155
    Prev
    Next
    INDEX
    Explanations

    zero-cost abstractions and cost

    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
     NodeType
    0.40
    followfollow
    0.38
    Tatar
    0.38
    azure
    0.38
    zü
    0.38
     ginger
    0.37
    追
    0.37
    ंसर
    0.36
    كتب
    0.36
    chinese
    0.36
    POSITIVE LOGITS
    িশ
    0.42
     कोशिश
    0.38
     측
    0.36
     militia
    0.35
     practicable
    0.35
     Alderman
    0.35
     hoods
    0.35
    Pool
    0.34
     unimportant
    0.34
    transformers
    0.34
    Activations Density 0.000%

    No Known Activations