© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2836
    Prev
    Next
    INDEX
    Explanations

    issues raised or not foreseeable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     judgement
    0.89
     Appeals
    0.87
     judgements
    0.85
     힘
    0.83
     jugement
    0.80
     maths
    0.79
     Decimal
    0.79
     রায়
    0.78
     결정
    0.76
     hehe
    0.76
    POSITIVE LOGITS
     affirmatively
    1.35
     pursuant
    1.19
     reasonably
    1.16
     proxim
    1.13
    reasonably
    1.09
     appellees
    1.05
     Defendant
    1.05
     Pursuant
    1.02
     "`
    1.01
     substantially
    1.00
    Activations Density 1.046%

    No Known Activations