© 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. 22-GEMMASCOPE-2-RES-16K
    7. 89
    Prev
    Next
    INDEX
    Explanations

    strengths

    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_22_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
    ATHER
    0.64
     ae
    0.62
    ‚
    0.59
     Wy
    0.58
     beg
    0.58
     technically
    0.56
     再
    0.55
    كري
    0.54
    ัท
    0.54
    ACH
    0.54
    POSITIVE LOGITS
     gonflement
    1.19
     destaque
    1.07
    planilla
    1.07
     vaisse
    1.06
    erkraut
    1.06
     उपभोक्ताओं
    1.06
     consente
    1.06
     ventaja
    1.06
    㧋
    1.05
    tsprec
    1.05
    Activations Density 0.053%

    No Known Activations