© 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. 7-GEMMASCOPE-2-RES-16K
    7. 115
    Prev
    Next
    INDEX
    Explanations

    positive states and environments

    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
    7
    1.93
    4
    1.85
    3
    1.84
    2
    1.84
    5
    1.81
    8
    1.75
    1
    1.73
    9
    1.71
    0
    1.71
    6
    1.69
    POSITIVE LOGITS
     inconsistency
    1.55
    ｓ
    1.54
     inconsistent
    1.51
     pushed
    1.49
     fairly
    1.48
     fatigued
    1.47
     twofold
    1.46
    ್‌
    1.45
     shortness
    1.44
     optimal
    1.42
    Activations Density 2.839%

    No Known Activations