© 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. 17-GEMMASCOPE-2-RES-16K
    4. 1719
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

    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_17_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
    .}
    0.71
    ;}
    0.69
     بلکہ
    0.69
    enschap
    0.68
    মানা
    0.67
    }}}
    0.67
     Tada
    0.66
    }}
    0.65
     कोने
    0.65
     But
    0.64
    POSITIVE LOGITS
    ാര്‍
    0.68
    final
    0.67
     vaksin
    0.59
    sono
    0.58
     لحاظ
    0.58
    对我
    0.57
     estime
    0.57
    `/
    0.57
     Vul
    0.56
    始まった
    0.56
    Activations Density 0.229%

    No Known Activations