© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 4841
    Prev
    Next
    INDEX
    Explanations

    numbers and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite

    sexual assault hotlines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_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
    <0xB2>
    0.64
     Sixth
    0.59
     шесть
    0.54
    We
    0.52
     six
    0.52
    six
    0.52
     Мы
    0.51
     sixth
    0.51
    Sixth
    0.50
     Six
    0.48
    POSITIVE LOGITS
    ২০
    0.50
     ہمارے
    0.44
     جہاں
    0.43
     ৫০
    0.42
    㑓
    0.42
    ﺤ
    0.41
     влас
    0.40
     наверное
    0.40
    庚
    0.40
     ২০
    0.40
    Activations Density 0.275%

    No Known Activations