© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11
    Prev
    Next
    INDEX
    Explanations

    code, security, feelings, legal clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Prothorax
    2.11
    '*
    1.97
    AsString
    1.92
    LOTRE
    1.92
    "*
    1.87
     DETER
    1.87
    IMPORTANT
    1.87
    Proof
    1.86
    CLASSI
    1.82
     Hydrochloride
    1.82
    POSITIVE LOGITS
    opo
    1.50
    ħ
    1.43
    रान
    1.37
    ian
    1.36
     छठ
    1.34
    acs
    1.33
    ivist
    1.31
    nels
    1.29
    amorph
    1.29
     bw
    1.28
    Activations Density 0.000%

    No Known Activations