© 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. 183
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    '
    1.10
     came
    1.05
     Productions
    1.04
    様専用
    1.02
     of
    1.00
     was
    1.00
     Μ
    1.00
     リ
    0.99
     від
    0.99
     from
    0.98
    POSITIVE LOGITS
     deleterious
    1.19
     undesirable
    1.14
    一定的
    1.14
    <unused1248>
    1.13
     potentialities
    1.12
     vattum
    1.10
     perturbations
    1.10
     ambiguities
    1.07
     multiplicities
    1.06
    besiege
    1.06
    Activations Density 7.828%

    No Known Activations