© 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
    2. Gemma-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-16K
    4. 11810
    Prev
    Next
    INDEX
    Explanations

    policy prohibiting content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
    )
    0.74
     ঘ
    0.73
    Type
    0.73
     পো
    0.71
     बनाता
    0.71
     मकसद
    0.70
    .
    0.70
    creating
    0.70
     w
    0.69
     blir
    0.69
    POSITIVE LOGITS
     adorable
    0.95
     rejoice
    0.91
    斋
    0.91
    gallon
    0.90
     heavens
    0.89
     indulged
    0.88
     illustrious
    0.88
     गर्ल
    0.88
    SCALE
    0.88
     Eich
    0.87
    Activations Density 0.000%

    No Known Activations