© 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
    3. 7-GEMMASCOPE-2-RES-16K
    4. 14090
    Prev
    Next
    INDEX
    Explanations

    various types of collapse

    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
    о
    2.32
    ».
    2.26
    »
    2.26
    <bos>
    2.26
    光
    2.25
    йма
    2.16
    का
    2.09
    into
    2.09
     fix
    2.09
    ))$,
    2.08
    POSITIVE LOGITS
    lungs
    2.95
    foils
    2.85
    ','')
    2.76
    PublicKey
    2.70
     }_{
    2.66
    ్యాచ్
    2.65
    lung
    2.65
    вање
    2.63
    瘓
    2.57
     finan
    2.51
    Activations Density 0.022%

    No Known Activations